Merge tag 'kvm-ppc-next-4.20-2' of...

Merge tag 'kvm-ppc-next-4.20-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

Second PPC KVM update for 4.20.

Two commits; one is an optimization for PCI pass-through, and the
other disables nested HV-KVM on early POWER9 chips that need a
particular hardware bug workaround.

arch/powerpc/include/asm/iommu.h

@@ -126,7 +126,7 @@ struct iommu_table {
 	int it_nid;
 };
 
-#define IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry) \
+#define IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry) \
 		((tbl)->it_ops->useraddrptr((tbl), (entry), false))
 #define IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry) \
 		((tbl)->it_ops->useraddrptr((tbl), (entry), true))

arch/powerpc/kvm/book3s_64_vio.c

@@ -410,11 +410,10 @@ static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 
 	if (!pua)
-		/* it_userspace allocation might be delayed */
-		return H_TOO_HARD;
+		return H_SUCCESS;
 
 	mem = mm_iommu_lookup(kvm->mm, be64_to_cpu(*pua), pgsize);
 	if (!mem)

arch/powerpc/kvm/book3s_64_vio_hv.c

@@ -214,7 +214,7 @@ static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
 
 	if (!ret && ((*direction == DMA_FROM_DEVICE) ||
 				(*direction == DMA_BIDIRECTIONAL))) {
-		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+		__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 		/*
 		 * kvmppc_rm_tce_iommu_do_map() updates the UA cache after
 		 * calling this so we still get here a valid UA.
@@ -240,7 +240,7 @@ static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
 {
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 
 	if (!pua)
 		/* it_userspace allocation might be delayed */
@@ -304,7 +304,7 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 {
 	long ret;
 	unsigned long hpa = 0;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RM(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 	struct mm_iommu_table_group_mem_t *mem;
 
 	if (!pua)

arch/powerpc/kvm/book3s_hv.c

@@ -4174,7 +4174,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
-		if (kvm->arch.threads_indep && kvm_is_radix(kvm))
+		/*
+		 * The early POWER9 chips that can't mix radix and HPT threads
+		 * on the same core also need the workaround for the problem
+		 * where the TLB would prefetch entries in the guest exit path
+		 * for radix guests using the guest PIDR value and LPID 0.
+		 * The workaround is in the old path (kvmppc_run_vcpu())
+		 * but not the new path (kvmhv_run_single_vcpu()).
+		 */
+		if (kvm->arch.threads_indep && kvm_is_radix(kvm) &&
+		    !no_mixing_hpt_and_radix)
 			r = kvmhv_run_single_vcpu(run, vcpu, ~(u64)0,
 						  vcpu->arch.vcore->lpcr);
 		else
@@ -5196,7 +5205,7 @@ static int kvmhv_enable_nested(struct kvm *kvm)
 {
 	if (!nested)
 		return -EPERM;
-	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+	if (!cpu_has_feature(CPU_FTR_ARCH_300) || no_mixing_hpt_and_radix)
 		return -ENODEV;
 
 	/* kvm == NULL means the caller is testing if the capability exists */

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -444,7 +444,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 	struct mm_iommu_table_group_mem_t *mem = NULL;
 	int ret;
 	unsigned long hpa = 0;
-	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl, entry);
 
 	if (!pua)
 		return;
@@ -467,8 +467,27 @@ static int tce_iommu_clear(struct tce_container *container,
 	unsigned long oldhpa;
 	long ret;
 	enum dma_data_direction direction;
+	unsigned long lastentry = entry + pages;
+
+	for ( ; entry < lastentry; ++entry) {
+		if (tbl->it_indirect_levels && tbl->it_userspace) {
+			/*
+			 * For multilevel tables, we can take a shortcut here
+			 * and skip some TCEs as we know that the userspace
+			 * addresses cache is a mirror of the real TCE table
+			 * and if it is missing some indirect levels, then
+			 * the hardware table does not have them allocated
+			 * either and therefore does not require updating.
+			 */
+			__be64 *pua = IOMMU_TABLE_USERSPACE_ENTRY_RO(tbl,
+					entry);
+			if (!pua) {
+				/* align to level_size which is power of two */
+				entry |= tbl->it_level_size - 1;
+				continue;
+			}
+		}
 
-	for ( ; pages; --pages, ++entry) {
 		cond_resched();
 
 		direction = DMA_NONE;